Required Technologies

Starter Applications

Participants must build on top of one of these two applications!

• Microservices Demo (Online Boutique) repo on GitHub

• Development Guide for Microservices Demo

• Bank of Anthos repo on GitHub

• Development Guide for Bank of Anthos

Google Kubernetes Engine (required)

Participants must design their code to run on GKE!

• GKE Documentation and Quickstart
• Skills Boost courses & labs
• Join the Google Cloud Innovators community to get 35 credits on Skills Boost 
• GKE 10 years: What our customers are saying on AI on GKE
• GKE Signify case study (case study)
• Agentic AI: The Next Evolution of Microservices? (webinar)
• Unlocking AI innovation on GKE with Moloco (webinar)
• GKE Inference Video

Recommended Technologies:

The below technologies may be helpful as you build your service.

AI Agents

• What is an AI Agent? 
• AI Agent Bakeoff
• Agents Whitepaper (2024)
• Agents Companion Whitepaper (Apr 2025)

Agent Development Kit (optional)

Agent Development Kit (ADK) is a flexible and modular framework for developing and deploying AI agents.

• ADK Docs - Deploy to GKE
• ADK docs use the quickstart, checkout tools (function, built-in, GCP, MCP, OpenAPI, etc), use adk web locally and deploy.
• ADK sample agents reference our agents or edit and use these as part of your multi-agent system.
• ADK videos watch intros and deep dive videos to understand your options.
• ADK github review the repo for more details and contribute with a PR.

Agent2Agent (A2A) Protocol (optional)

A2A is an open protocol enabling communication and interoperability between opaque agentic applications.

• A2A repo on GitHub
• A2A Docs

Model Context Protocol (MCP) (optional)

MCP is an open protocol that standardizes how applications provide context to LLMs.

• MCP Docs

kubectl-ai (optional)

kubectl-ai acts as an intelligent interface, translating user intent into precise Kubernetes operations, making Kubernetes management more accessible and efficient.

• kubectl-ai repo

Gemini CLI (optional)

Gemini CLI is a command-line AI workflow tool that connects to your tools, understands your code and accelerates your workflows.

• Gemini CLI repo on GitHub
• Gemini CLI in the Google Cloud docs
• Gemini CLI announcement blog

Download: How to Accelerate AI Innovation with Containers EBook

Access to Google Cloud

If you’re new to Google Cloud, sign up for a Google Developer account and get $300 in Google Cloud credits

If you already have a Google Cloud account, request $100 in Google Cloud credits here.

INSPIRATION

Potential examples for creativity include:

• Adding a sophisticated AI chatbot to the Online Boutique that can query inventory, provide product recommendations, or even check a user's financial balance via an integrated Bank of Anthos API.

• Developing an agent that monitors microservice performance on GKE and suggests troubleshooting steps or automates remediation, leveraging the Kubernetes troubleshooting agent idea.

• Creating a "non-traditional GKE use case" by integrating AI in a unique or unexpected way with the microservices.